EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Prediction of Lower-Limb Joint Kinematics, Kinetics, and Ground Reaction Force Using Wearable Sensors and Machine Learning

Josée Mallah iD, Yu Zhu, Kailang Xu iD, Gurvinder S Virk, Shaoping Bai iD, Luigi G Occhipinti iD

Sensors · 2026

DOI: 10.3390/s26185885 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Josée Mallah und 5 weiteren Autor:innen. Beteiligte Einrichtung: Electrical Engineering Division, Department of Engineering, University of Cambridge, Cambridge CB3 0FA, UK. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Machine Learning, Lower Extremity, Joints. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MathWorks (United Kingdom), Cambridge Commonwealth European and International Trust.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Walking is a key movement of interest in biomechanics, yet gold-standard data collection methods are time- and cost-expensive. This paper presents a real-time, multimodal, high sample rate lower-limb motion capture framework, based on wireless wearable sensors and machine learning algorithms. Random Forests are used to estimate joint angles from IMU data, and ground reaction force (GRF) is predicted from an instrumented insole, while joint moments are predicted from angles and GRF using deep learning based on the ResNet-16 architecture. All three models achieve good accuracy compared to the literature, and the predictions are logged at 1 kHz with a minimal delay of 23 ms for 20s worth of input data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesMachine LearningLower ExtremityJointsHumansBiomechanical PhenomenaKineticsAlgorithmsMotion CapturePrediction AlgorithmsWalkingRandom ForestPredictive Learning Models

Stichwörter der Autor:innen

biomechanicsmachine learningreal-time systemswearable sensors

Autor:innen und Institutionen

  • Electrical Engineering Division, Department of Engineering, University of Cambridge, Cambridge CB3 0FA, UK.
  • Department of Electronic Systems, Aalborg University, 9220 Aalborg, Denmark.
  • Endoenergy Systems Ltd., Cambridge CB25 0HG, UK.
  • Huzhou Wuxing District Intelligent Robot Innovation Research Institute, Huzhou 313000, China.
  • Department of Materials and Production, Aalborg University, 9220 Aalborg, Denmark.
  • Wolfson School of Mechanical, Electrical and Manufacturing Engineering, Loughborough University, Loughborough LE11 3TU, UK.

ORCID-Profile: Josée Mallah, Kailang Xu, Shaoping Bai, Luigi G Occhipinti

Förderung

  • MathWorks (United Kingdom)
  • Cambridge Commonwealth European and International Trust

Zitieren

APA

Mallah, J., Zhu, Y., Xu, K., Virk, G. S., Bai, S., & Occhipinti, L. G. (2026). Real-Time Prediction of Lower-Limb Joint Kinematics, Kinetics, and Ground Reaction Force Using Wearable Sensors and Machine Learning. Sensors. https://doi.org/10.3390/s26185885

Vancouver

Mallah J, Zhu Y, Xu K, Virk GS, Bai S, Occhipinti LG. Real-Time Prediction of Lower-Limb Joint Kinematics, Kinetics, and Ground Reaction Force Using Wearable Sensors and Machine Learning. Sensors. 2026. doi:10.3390/s26185885

BibTeX
@article{Mallah2026,
  author = {Mallah, Josée and Zhu, Yu and Xu, Kailang and Virk, Gurvinder S and Bai, Shaoping and Occhipinti, Luigi G},
  title = {Real-Time Prediction of Lower-Limb Joint Kinematics, Kinetics, and Ground Reaction Force Using Wearable Sensors and Machine Learning},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26185885}
}
Kostenlos starten →